Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    RB
    0.74
    engin
    0.73
     RO
    0.71
     catchment
    0.71
    fet
    0.70
    GORITHM
    0.70
     RMB
    0.68
     amenity
    0.68
    RL
    0.68
    amp
    0.68
    POSITIVE LOGITS
    ਇ
    1.03
    இந்த
    0.90
     修
    0.89
    資格
    0.86
     சித்த
    0.85
    建设
    0.84
    ᅪ
    0.83
     distracting
    0.83
     каж
    0.81
    𝗋
    0.79
    Act Density 0.000%

    No Known Activations